Risk management and portfolio selection using \alpha-stable regime switching models

Abstract

This article tries to enhance traditional distribution paradigms for modelling asset returns by considering an α-stable regime-switching model. Our approach is to perform an empirical test of the α-stable regimeswitching model against other common methods in two settings: in risk management and in portfolio selection. Our empirical study will show that the model is better suited than Gaussian and Gaussian regimeswitching models to measure risk accurately. A portfolio optimization case study for a traditional stocks and bonds investor is pursued. In this study, the model leads to less risky and more diversified portfolios. In particular, the model avoids outsized losses in times of crisis and thus leads to a better (adjusted) Sharpe ratio and Omega.

Fractal analysis of market (in)efficiency during the COVID-19

“…To date, an impressive literature has focused on volatility and volatility clustering, and - since the pioneering work by Mandelbrot (1963) - many models have been proposed to account for the time-varying volatility of price variations: the -stable distributions ( Rachev and Mittnik (1993) ; Samorodnitsky and Taqqu (1994) ; Rachev and Mittnik (2000) , Reussa et al. (2016) ), whose main drawback is to be infinite variance models; the ARCH-GARCH-based family ( Engle (1982) ; Bollerslev (1986) ; see Alexander (2001) or Francq and Zakoian (2019) for a complete review), whose residuals are anyway still fat-tailed and dependent, which is a clear symptom that volatility is not completely captured by the model; and the stochastic volatility models ( Hull and White (1990) , Heston (1993) , Dupire (1994) ), whose main idea is that volatility follows a diffusion process.…”